-
Optimize OpenSearch Refresh Interval
Learn how to optimize the refresh interval of an OpenSearch index and strike a balance between the speed at which indexed information is available for search with CPU and I/O costs
Read More -
What in the ML is going on around here?
Going from a vanilla install of OpenSearch to having vectorized text stored in a k-NN–enabled index seemed like a quick learning exercise. On paper, it almost looked easy. Upload a model to a node designated as a ML node, load it, and start ingesting text and storing it as a vector. The amount of probing, asking, experimenting, and copying and...
Read More -
Introducing a traffic capture and replay solution for OpenSearch migrations and upgrades
We are thrilled to introduce the beta release of a live traffic capture and replay solution designed to assist users in migrating to OpenSearch. This tool equips users to capture live traffic from their source cluster and replay it, either simultaneously or offline, on a specified shadow cluster for rigorous testing and analysis. By comparing the performance and behavior of...
Read More -
Efficient filtering in OpenSearch vector engine
With the release of OpenSearch 2.9, we introduced efficient filtering, or “filter-while-search,” functionality for queries using the Facebook AI Similarity Search (Faiss) engine. This update overcomes the previous limitations of pre-filtering and post-filtering in the OpenSearch vector engine. In the OpenSearch 2.10 release, we added support for filtering using the inverted file (IVF) algorithm and further improved the overall performance...
Read More -
Introducing concurrent segment search in OpenSearch
OpenSearch is a scalable, flexible, and extensible open-source search and analytics engine. It is built on top of Apache Lucene and uses its powerful capabilities to ingest user data and serve search requests with latency in milliseconds.
Read More